Comparison and design of interpretable linguistic vs. scatter FRBSs: Gm3m generalization and new rule meaning index for global assessment and local pseudo-linguistic representation

摘要: This work is devoted to defining more general interpretability indexes be applied any scatter or linguistic model implemented by type of membership functions. They are based on metrics that should take into account the semantic and inference issues: issue in order preserve meaning labels since this can influence behavior rules. On other hand, these have been designed intuitive support analysis selection a final favor low computational cost within an optimization process. In check their usefulness, multi-objective evolutionary algorithm, simultaneously performing rule adjustment fuzzy partitions, guided proposed several benchmark data sets obtain models with different degrees accuracy interpretability. addition, using metrics, local carried out between nature. through components, gives user make best choice from among models.